Convergence analysis of a family of Zermelo-type iterations for the Bradley--Terry model

2026-07-24

AI Summary

This work addresses the slow convergence of the classical Zermelo algorithm in the Bradley–Terry model and the lack of theoretical justification for existing acceleration strategies. The authors systematically investigate a family of Zermelo-type iterative algorithms parameterized by α, analyzing their local convergence behavior under both synchronous and asynchronous updates. They theoretically establish that the accelerated convergence observed at α = 0 fundamentally arises from the asynchronous update mechanism and prove that this choice achieves the optimal local convergence rate on certain graph structures. Through spectral analysis of the Jacobian matrix, derivation of local convergence factors, and asymptotic approximation techniques, the study rigorously demonstrates that asynchronous updates with α = 0 yield the fastest local convergence. Extensive experiments on synthetic and real-world data corroborate the theoretical findings.

Abstract

Zermelo's algorithm is a classical method for computing the maximum likelihood estimator in the Bradley--Terry (BT) model, but its convergence can be slow in practice. To accelerate computation, Newman introduced a family of Zermelo-type fixed-point iterations parameterized by $α$, with Zermelo's algorithm recovered at $α=1$. Empirical evidence suggests that the choice $α=0$ often converges substantially faster, making it a promising alternative, yet the mechanism underlying this acceleration remains elusive. This paper provides theoretical insight into this phenomenon through a systematic local convergence analysis. We derive closed-form expressions for local convergence factors under synchronous and asynchronous updates and analyze their dependence on $α$ via spectral analysis of the associated Jacobian matrices. For synchronous updates, we show that the algorithm may fail to converge when $α<1$, and its local convergence factor is quasi-convex in $α$ under the population BT model. In contrast, asynchronous updates are always locally convergent, and their local convergence factor is provably monotonically increasing in $α$ under the population BT model of consistently ordered bipartite comparison graphs, establishing the optimality of $α=0$ in this setting. We further establish asymptotic approximation results for the population convergence factors under the BT model, justifying their practical relevance. Numerical experiments on synthetic and real-world datasets confirm the theory. Our analysis complements existing convergence results and shows that the acceleration of $α=0$ arises not only from the parameter choice but, more importantly, from the use of asynchronous updates.

Problem

• Bradley-Terry model
• Zermelo's algorithm
• convergence analysis
• asynchronous updates
• fixed-point iterations

Innovation

• Zermelo-type iteration
• Bradley-Terry model
• asynchronous update
• local convergence analysis
• spectral analysis